Voiceprint extraction helm chart

Phonexia Speaker Identification (SID) extractor

Maintainers

Name	Email	Url
Phonexia	support@phonexia.com	https://www.phonexia.com

Helm: >= 3.2.0

Values

Key	Type	Default	Description
affinity	object	{}	Affinity for pod assignment
annotations	object	{}
config.device	string	"cpu"	Compute device used for inference Can be cpu or cuda If you use cuda you have to use also image tag with gpu support
config.instancesPerDevice	int	1	Parallel tasks per device. GPU only.
config.keepAliveTime	int	60	Time between 2 consecutive keep-alive messages, that are sent if there is no activity from the client.
config.keepAliveTimeout	int	20	Time to wait for keep alive acknowledgement until the connection is dropped by the server.
config.license.useSecret	bool	false	Get license from secret object
config.license.value	string	"invalidLicenseKey"	License key
config.listeningAddress	string	"[::]"	Override address where the server will listen
config.logLevel	string	info	Override log level Supported values: error, warning, info, debug, trace
config.model.file	string	""	Name of a model file inside the volume, for example "xl-5.0.0.model"
config.model.volume	object	{}	Volume with Phonexia model
config.port	int	8080	Port where the service will listen. The value must be same as service.port.
config.threadsPerInstance	int	1	Number of threads to use when running on CPU
extraEnvVars	list	[]
fullnameOverride	string	""	String to fully override voiceprint-extraction.fullname template
image.pullPolicy	string	"IfNotPresent"	Image pull policy
image.registry	string	"registry.cloud.phonexia.com"	Image registry
image.repository	string	"phonexia/dev/technologies/microservices/voiceprint-extraction"	Image repository
image.tag	string	appVersion specified in Chart.yaml	See voiceprint-extraction on dockerhub for available tags
imagePullSecrets	list	[]	Specify docker-registry secret names as an array
ingress.annotations	object	{}
ingress.className	string	""
ingress.enabled	bool	false
ingress.hosts[0]	object	{"host":"voiceprint-extraction.example.com","paths":[{"path":"/","pathType":"ImplementationSpecific"}]}	Default host for the ingress resource
ingress.hosts[0].paths[0].pathType	string	"ImplementationSpecific"	Ingress path type
ingress.tls	list	[]
initContainers	list	[]	Init containers Evaluated as a template.
livenessProbe	object	{"failureThreshold":3,"initialDelaySeconds":0,"periodSeconds":10,"successThreshold":1,"timeoutSeconds":1}	Liveness probe settings
nameOverride	string	""	String to partially override voiceprint-extraction.fullname template (will maintain the release name)
nodeSelector	object	{}	Node labels for pod assignment.
podAnnotations	object	{}	Annotations for pods
podSecurityContext	object	{}	Security context for pods
readinessProbe	object	{"failureThreshold":3,"initialDelaySeconds":0,"periodSeconds":10,"successThreshold":1,"timeoutSeconds":1}	Readiness probe settings
replicaCount	int	1	Number of replicas to deploy
resources	object	{}	The resources limits/requests for the voiceprint-extraction container
runtimeClassName	string	""	Specify runtime class
securityContext	object	{}	Security context for voiceprint-extraction container
service.clusterIP	string	""	Use None to create headless service
service.port	int	8080	Service port The port must be same as config.port
service.type	string	"ClusterIP"	Service type
serviceAccount.annotations	object	{}	Annotations to add to the service account
serviceAccount.create	bool	true	Specifies whether a service account should be created
serviceAccount.name	string	""	The name of the service account to use. If not set and create is true, a name is generated using the fullname template
tolerations	list	[]	Tolerations for pod assignment.
updateStrategy	object	{"type":"RollingUpdate"}	Deployment update strategy

Installation

To successfully install the chart you have to obtain license and model at first. Service is unable to start without model and/or license. Feel free to contact phonexia support to obtain model and license for evaluation purpose.

Model

There are 2 ways how to pass a model to pods:

• Pass the model via initContainer
• Pass the model via volume

Pass the model via initContainer

With this approach no persistent volume is needed. InitContainer is added to the pod instead. It downloads model from specified location to ephemeral volume which is shared with main container. This happens each time when pod is re-deployed.

In values file it looks like:

# Set config.model.volume to emptyDir
config:
  model:
    volume:
       emptyDir: {}
    file: "xl-5.0.0.model"

initContainers:
  - name: init-copy-model
    image: alpine
    command:
      - sh
      - -c
      - |
        set -e

        # Install aws-cli package
        apk add --no-cache aws-cli

        # Create directory for models
        mkdir -p /models

        # Download model from s3 and store it to volume
        aws s3 cp s3://some-bucket/some-path-to-model/xl-5.0.0.model ${PHX_MODEL_PATH}
    env:
      # PHX_MODEL_PATH variable must be same as in main container
      - name: "PHX_MODEL_PATH"
        value: "/models/{{ .Values.config.model.file }}"
      # Set AWS_* variables to make aws cli work
      - name: "AWS_DEFAULT_REGION"
        value: "us-east-1"
      - name: "AWS_ACCESS_KEY_ID"
        value: "AKAI...CN"
      - name: "AWS_SECRET_ACCESS_KEY"
        value: "0lW...Yw"
    # Mount empty volume to initContainer
    volumeMounts:
      - name: '{{ include "voiceprint-extraction.fullname" . }}-models-volume'
        mountPath: /models

Pass the model via volume

With this approach you need to create persistent volume, copy model there and mount it to pod.

Following example shows how to do it in EKS with EBS-based dynamic provisioning.

1. Create persistentVolumeClaim

# filename: voiceprint-extraction.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: voiceprint-extraction
spec:
  accessModes:
  - ReadWriteOnce
  resources:
    requests:
      storage: 10Gi
  storageClassName: ebs-sc

and apply it

kubectl apply -f voiceprint-extraction.yaml

2. Create job which downloads model to persistent volume:

# filename: job.yaml
apiVersion: batch/v1
kind: Job
metadata:
  name: voiceprint-extraction-download-model
spec:
  template:
    spec:
      containers:
        - name: download-model
          image: alpine
          command:
            - sh
            - -c
            - |
              set -e

              # Install aws-cli package
              apk add --no-cache aws-cli

              # Create directory for models
              mkdir -p /models

              # Download model from s3 and store it to volume
              aws s3 cp s3://some-bucket/some-path-to-model/xl-5.0.0.model ${PHX_MODEL_PATH}
          env:
            # PHX_MODEL_PATH variable must be same as .Values.config.model.file in values files
            - name: "PHX_MODEL_PATH"
              value: "/models/xl-5.0.0.model"
            # Set AWS_* variables to make aws cli work
            - name: "AWS_DEFAULT_REGION"
              value: "us-east-1"
            - name: "AWS_ACCESS_KEY_ID"
              value: "AKAI...CN"
            - name: "AWS_SECRET_ACCESS_KEY"
              value: "0lW...Yw"
          volumeMounts:
            - name: persistent-storage
              mountPath: /models
      volumes:
        - name: persistent-storage
          persistentVolumeClaim:
            claimName: voiceprint-extraction
      restartPolicy: Never
  backoffLimit: 3

Apply it and wait until job is finished:

kubectl apply -f job.yaml

3. Configure values file to use existing PVC:

config:
  model:
    # Volume with Phonexia model
    volume:
      persistentVolumeClaim:
        claimName: voiceprint-extraction

    # Name of a model file inside the volume, for example "xl-5.0.0.model"
    file: "xl-5.0.0.model"

License

There are 2 ways how to pass license key to the chart:

• Pass the license key directly into values files
• Pass the license key via kubernetes secret

Pass the license key directly into values files

Use config.license.value to set license key in values file:

config:
  license:
    useSecret: false
    value: "<license_key>"

Replace <license_key> with license key which is a long string, something like eyJ...ifQ==.

Pass the license key via kubernetes secret

Create kubernetes secret at first:

kubectl --namespace <my-namespace> create secret generic <my-secret> --from-literal=license=<license_key>

where <my-namespace> is namespace where you plan to install the chart, my-secret is name of the secret to be created and <license_key> is actual license key.

In the end it should look like:

kubectl --namespace my-namespace create secret generic my-secret --from-literal=license=eyJ...ifQ==

Reference the secret in values file:

config:
  license:
    useSecret: true
    secret: "my-secret"
    key: "license"

Installing the Chart

When you have configure model and license you can proceed with installation itself. To install the chart with the release name my-release:

helm install my-release oci://registry-1.docker.io/phonexia/voiceprint-extraction

This command deploy voiceprint-extraction on the Kubernetes cluster in the default configuration.

Use --version parameter to install specific version:

helm install my-release oci://registry-1.docker.io/phonexia/voiceprint-extraction --version 1.0.0-helm

Exposing the service

To expose the service outside of kubernetes cluster follow Using a Service to Expose Your App.

Ingress

Voiceprint extraction service is using GRPC protocol which can be exposed by some ingress controllers. For example nginx-ingress controller support this. To expose voiceprint-extraction service via ingress use following configuration:

ingress:
  # Deploy ingress object
  enabled: true
  # Ingress class name
  className: "nginx"
  annotations:
    # Force redirect to SSL
    nginx.ingress.kubernetes.io/ssl-redirect: "true"

    # Tell nginx that backend service use GRPC
    nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
  hosts:
    # Hostnames
    - host: voiceprint-extraction.example.com
      paths:
        - path: /
          pathType: ImplementationSpecific
  # Use tls
  tls:
    # Secret containing TLS certificate
    - secretName: voiceprint-extraction-tls
      # TLS hostnames
      hosts:
        - voiceprint-extraction.example.com

Use grpcurl to check if everything works as expected. Output of the following command

$ grpcurl --insecure voiceprint-extraction.example.com:443 grpc.health.v1.Health/Check

should be

{
  "status": "SERVING"
}

Uninstalling the Chart

To uninstall/delete the my-release release:

helm delete my-release

The command removes all the Kubernetes components associated with the chart and deletes the release.